English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

High-confidence overlap prediction and accurate correspondences are criticalfor cutting-edge models to align paired point clouds in a partial-to-partialmanner. However, there inherently exists uncertainty between the overlappingand non-overlapping regions, which has always been neglected and significantlyaffects the registration performance. Beyond the current wisdom, we propose anovel uncertainty-aware overlap prediction network, dubbed UTOPIC, to tacklethe ambiguous overlap prediction problem; to our knowledge, this is the firstto explicitly introduce overlap uncertainty to point cloud registration.Moreover, we induce the feature extractor to implicitly perceive the shapeknowledge through a completion decoder, and present a geometric relationembedding for Transformer to obtain transformation-invariant geometry-awarefeature representations. With the merits of more reliable overlap scores andmore precise dense correspondences, UTOPIC can achieve stable and accurateregistration results, even for the inputs with limited overlapping areas.Extensive quantitative and qualitative experiments on synthetic and realbenchmarks demonstrate the superiority of our approach over state-of-the-artmethods.

UTOPIC: Uncertainty-aware Overlap Prediction Network for Partial Point Cloud Registration